CRNN (with BEATs)

Reported on 5 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio5 results

Sound Event DetectiononWildDESED
PSDS1 (Clean)· uses extra data· 2024-11-02
0.5
SOTA
Leveraging LLM and Text-Queried Separation for Noise-Robust Sound Event Detection arXiv:2411.01174
Sound Event DetectiononWildDESED
PSDS1 (-5dB)· uses extra data· 2024-11-02
0.065
best: 0.134 (CRNN (with BEATs + Separation))
Leveraging LLM and Text-Queried Separation for Noise-Robust Sound Event Detection arXiv:2411.01174
Sound Event DetectiononWildDESED
PSDS1 (0dB)· uses extra data· 2024-11-02
0.138
best: 0.219 (CRNN (with BEATs + Separation))
Leveraging LLM and Text-Queried Separation for Noise-Robust Sound Event Detection arXiv:2411.01174
Sound Event DetectiononWildDESED
PSDS1 (10dB)· uses extra data· 2024-11-02
0.329
best: 0.356 (CRNN (with BEATs + Separation))
Leveraging LLM and Text-Queried Separation for Noise-Robust Sound Event Detection arXiv:2411.01174
Sound Event DetectiononWildDESED
PSDS1 (5dB)· uses extra data· 2024-11-02
0.236
best: 0.291 (CRNN (with BEATs + Separation))
Leveraging LLM and Text-Queried Separation for Noise-Robust Sound Event Detection arXiv:2411.01174